Loading [MathJax]/extensions/MathMenu.js
Reinforcement Learning Approach to Improve Transmission Control Protocol | IEEE Conference Publication | IEEE Xplore

Reinforcement Learning Approach to Improve Transmission Control Protocol


Abstract:

Transmission Control Protocol(TCP) plays an important role in everyday life, right from accessing ones mails to browsing the internet. With revolutionary mechanisms to en...Show More

Abstract:

Transmission Control Protocol(TCP) plays an important role in everyday life, right from accessing ones mails to browsing the internet. With revolutionary mechanisms to ensure safe and consistent delivery of data and reducing the loss in the data transferred, TCP has indeed paved way for a paradigm shift in the way data is delivered over a network. TCP is proven to work in traditional environments involving conventional wired transmission, with well formulated packet loss restricting mechanisms implemented in the form of congestion control techniques. It is, however, found wanting in environments which involve a degree of heterogeneity (composed of wired and wireless nodes) or in purely wireless networks, involving multimedia data transmission. The performance improvement is achieved by developing a system that can classify losses as occurring due to congestion or due to the wireless nature and consequently controlling the congestion window size. This work seeks to create such a system based on reinforcement learning, where it first learns to differentiate and then predict wireless and congestion loss and consequently, predict the ideal size of congestion window thereby increasing the throughput of the system.
Date of Conference: 21-23 February 2019
Date Added to IEEE Xplore: 11 October 2019
ISBN Information:
Conference Location: Chennai, India

I. Introduction

The protocol that is being used widely in the internet now is the Transmission Control Protocol(TCP). It establishes secure connection between the sender and receiver and this helps in reliable transmission of data. TCP considers a packet to be lost when the receiver doesn’t send any acknowledgment before the timeout period, which is calculated by the sender. After receiving the packet, the receiver sends an acknowledgment implicitly or explicitly. If the sender does not receive an acknowledgment before the round trip time period, then the packet is retransmitted. To prevent the traffic in the network and to regulate it, the congestion window sets its value dynamically based on the current condition of the network. Initially, the main objective of TCP was to use the bandwidth efficiently without overloading the network(and hence prevent packet losses) by controlling the sender receiver transmission rates. Packets are lost mainly due to congestion in the network.

Contact IEEE to Subscribe

References

References is not available for this document.